Local-first MCP server that reports real token usage and cost across coding agents (Claude Code, OpenCode, Codex CLI). Nothing leaves your machine.

Token usage auditor for AI coding tools. Investigate context bloat across Claude Code, Codex CLI & Gemini CLI.

MCP server for analyzing and optimizing context window token usage — audit tool definitions, compress schemas, track usage, and reduce bloat

Navigate, search and resume Claude Code and Codex sessions as numbered trees, with token usage per step. CLI + MCP plugin.

Token-level cost intelligence for Claude Code — per-project, per-agent, per-skill usage tracking with conversational MCP querying and local dashboard

Token usage across Claude Code, OpenCode, Codex & ZCode on one yardstick — plus a project memory and convention-debt tracker agents can query via MCP. No server, your data stays local.

Local-first MCP server that returns distilled, faithful code context to cut LLM token usage without degrading reasoning.

Cuts Claude Code and LLM token usage by 60-85% via AST navigation, deduplication, and context-budget optimization.

Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complementary tools (serena, RTK), and proactively surfaces savings tips.

Zero-dependency, fully-reversible context compression for AI agents — cut LLM token usage up to 94% (JSON tabularization, log template mining, query-aware code skeletons). Stdlib-only, air-gap ready, built-in MCP server.

Efficient code navigation MCP server - reduce Claude Code token usage by 95%+

Nuke your token usage. Code indexing MCP server: 15 tools, 10 languages, O(1) retrieval, hybrid search, call graphs.

MCP server for optimizing code references and reducing token usage through smart caching and AST parsing

MCP server + Claude Code Plugin for TOON format token optimization. Reduces token usage by 30-65% (typically 50-55%) on JSON/CSV/YAML data via multilingual-aware optimization.

Project management MCP server for AI-assisted development. Track tasks, conversations, decisions, token usage, and costs.

Token-slimming AST code outliner, log compressor & context budget analyzer for AI coding agents (Cursor, Claude, Cline, Antigravity). Slashes token usage & LLM API bills up to 85%.

Rust MCP server for lossless agent-context compression, reducing token usage while preserving retrieval accuracy.

MCP server for Confluence: returns storage XHTML files to LLMs, reducing token usage and preserving macros/tables on updates.

SigRank — ranks AI coding operators by token cascade efficiency (Yield = Cache Reads × Output / Input²). Tools for yield calculation, leaderboard queries, operator lookups, local token usage pulls, and signed token-count submission to the public board. Privacy-first: runs locally, only four token counts leave the machine (ed25519-signed). Install: npx sigrank

Claude Code plugin for MinniMemoryMCP (npm: minnimemory), which cuts Claude Code and Codex token usage. Generated from release builds.

Monitor and track AI coding activity in Claude Code — real-time analytics, token usage, cost tracking, rule enforcement. Zero overhead.

Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en

AI Mind Map — MCP server that reduces AI coding agent token usage by 80-99% through persistent codebase memory, knowledge graphs, and intelligent context management

MCP proxy that reduces token usage via TOON format

Local Tree-sitter code knowledge graph & MCP server that gives Claude Code, Cursor and other AI coding agents surgical edit context — cutting token usage by 80-95%.

Excel Claude Code Token Optimized MCP Server. Read-only live Excel access via peek tools and server-side aggregation, designed to minimize LLM token usage.

Stateful Pipeline MCP server for AI social agents — engage developer communities with minimal token usage

MCP server: Track AI agent token usage and API costs — npm wrapper

Claude Code plugins: work tracking, statusline lab, token-usage panes, GLM quota, readability + local-LLM MCP servers

Delegate your Taiga board to AI agents — an MCP server with per-agent scoped tokens, attribution, and usage metering

MCP server for AI agents — structured code analysis that cuts token usage by 87%

🧠 MCP server for semantic code search, cross-chat memory & token-slim routing — cut LLM token usage 80-95%. 100% local, no API keys. Works with Claude Code, Cursor, Codex, Hermes.

An advanced MCP server for browser automation using Puppeteer, optimized for minimal token usage while providing comprehensive data when needed.

Context Sherpa MCP server provides code mapping, deterministic feedback loops, and tiered inference for AI coding agents to increase accuracy and optimize token usage.

Capture local AI agent traces and inspect failures, approvals, token usage, and run regressions through MCP.

MCP server that gives AI coding agents the rdloom specs: props, usage rules, accessibility requirements, tokens and source.

Batch multiple MCP tool calls into a single request—reducing overhead and token usage for AI agents

Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges

🧠 Save 70–95% tokens in Claude Code, Cursor, Windsurf & Cline. Local Tree-sitter code graph MCP server: surgical edit context instead of full-file reads, refactor safety checks, and a hook that blocks large file reads. Reduce token usage & cost, zero LLM indexing.

Local MCP Server implementation for Obsidian . Allows multi-vault usage, optimized for token efficiency, and based on how markdown works.

MCP server that gives Claude persistent memory across sessions — reduces token usage by 70% by injecting only relevant context instead of full history.

A dedicated MCP (Model Context Protocol) server that connects directly to your LibreChat MongoDB database to provide real-time analytics on token usage, model consumption, and user activity.

AI-native .NET code intelligence for faster, more accurate codebase navigation with lower token usage.

ServiceNow MCP server with safe AI writes (plan, token, apply, journal, revert), find usages, flow tracing and drift checks over the full REST surface.

Token usage across Claude Code, OpenCode, Codex & ZCode on one yardstick — plus a project mem log and convention-debt tracker agents query via 3 MCP tools. No server, your data stays local

Visualize and diagnose OpenClaw context windows to identify token usage, file health, and available space for conversation.

iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group various Xcode/IDB tools based on your current workflow. [deprecated]

🧠 MCP Server that reduces AI coding agent token usage by 80-99%. Knowledge graph + persistent memory + smart compression for Claude, Cursor, Copilot, and any MCP-compatible agent.

Local knowledge graph for any project: zero-dependency indexer + 7-tool MCP server for Claude Code + live neumorphic graph UI. Cuts Claude token usage 8-10x.

Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.

Smarter reads, safer edits. An MCP plugin that cuts token usage and catches editing mistakes before they hit disk. Supports Claude Code, Gemini CLI, GitHub Copilot, and Codex.

MCP bridge for AI agents using Entroly Context Assurance: reduce avoidable AI token usage with evidence selection, receipts, exact recovery, and verification.

codebuddy-first bridge for DeepSeek Harness (DSH): prioritize the local codebuddy CLI in every mode (full DSH control, no prompts), with a rate-limit/network fallback dialog, a live status light (dynamic form + home-level plugin), per-project token usage

MCP Task Relay is a production-ready Model Context Protocol (MCP) server that exposes a sophisticated scheduler/executor workflow for autonomous agents. Built with enterprise-grade reliability, it features an intelligent Ask/Answer protocol with cryptographic context verification, preventing context drift while reducing token usage by 95%+.

Context Engineering is a MCP server that gives AI agents perfect understanding of your codebase. Eliminates context loss, reduces token usage, and generates comprehensive feature plans in minutes. Compatible with Cursor, Claude Code, and VS Code.

A 22-tool MCP server and CI-ready CLI that cuts cloud LLM token usage on code quality tasks. Deterministic tools handle what they can. A local LLM (via DSPy) handles the rest. Cloud models plan and review. Nothing else.

Reduce Claude Code token usage 54–67%. MCP server for web engineers — AI agents find symbols, trace callers, and map hierarchies by name instead of reading files. Built for TypeScript. Works with Claude Code, Cursor, and Codex.

Handy Coder is a local MCP server for coding assistants. It provides workspace tools for reading and editing files, searching code, running commands and tests, inspecting Git, and coordinating delegated tasks. The MCP is router-based so it reduces the tool definitions and schema context sent to an MCP client, which will lower prompt token usage.

Give AI coding agents a map before they read your code. Statically maps your codebase structure and dependencies, enriches components with LLM summaries, and links Git commits/Jira tickets to nodes. Optimizes agent context windows and token usage with compact, queryable JSON blueprints.

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.